EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LiDAR-Free 3D Auto-Labeling via Radar–Visual Spatio-Temporal Consistency

Boning Zhu iD, Zhiqun Hu iD, Zhaoming Lu

Sensors · 08.05.2026 · 26 (10) · 2956

DOI: 10.3390/s26102956 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.05.2026. Verfasst von Boning Zhu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing 100876, China. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision foundation models (VFMs) enable high-quality 2D instance masks, yet their lifted pseudo-point clouds suffer from scale ambiguity, structural noise, and temporal inconsistency, limiting their utility in 3D annotation. Existing automatic labeling methods either rely on expensive light detection and ranging (LiDAR) sensors or fail to enforce physical plausibility in dynamic roadside scenes. This study proposes a LiDAR-free radar–visual auto-labeling framework that leverages cross-modal spatio-temporal consistency between millimeter-wave radar trajectories and visual pseudo-point clouds to self-correct 3D geometry. The method first associates radar points, 2D masks, and pseudo-point clouds into object-centric sequences. Then, an uncertainty-aware pose fusion module combines motion-derived and structure-derived orientations using automatically solved road priors. Finally, the pseudo-point cloud is refined in canonical space by optimizing stable semantic landmarks from temporally consistent masks and propagating their corrections globally. Evaluated on a real-world roadside dataset, the method achieves 49.1% bird’s-eye-view (BEV) intersection over union (IoU) and 43.0% 3D IoU, outperforming a radar–camera fusion baseline by 5.5/5.9 points. Downstream experiments further show that the generated pseudo-labels and semantic enhancement are useful under the evaluated detector configurations, while broader validation remains future work.

Schlagwörter

Stichwörter der Autor:innen

LiDAR-free 3D auto-labelinggeometry refinementmillimeter-wave radarradar–camera fusionroadside perceptionspatio-temporal consistencyvisual foundation model

Autor:innen und Institutionen

  • Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing 100876, China.

ORCID-Profile: Boning Zhu, Zhiqun Hu

Zitieren

APA

Zhu, B., Hu, Z., & Lu, Z. (2026). LiDAR-Free 3D Auto-Labeling via Radar–Visual Spatio-Temporal Consistency. Sensors, 26(10), 2956. https://doi.org/10.3390/s26102956

Vancouver

Zhu B, Hu Z, Lu Z. LiDAR-Free 3D Auto-Labeling via Radar–Visual Spatio-Temporal Consistency. Sensors. 2026;26(10):2956. doi:10.3390/s26102956

BibTeX
@article{Zhu2026,
  author = {Zhu, Boning and Hu, Zhiqun and Lu, Zhaoming},
  title = {LiDAR-Free 3D Auto-Labeling via Radar–Visual Spatio-Temporal Consistency},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {2956},
  doi = {10.3390/s26102956}
}
Kostenlos starten →